arXiv cs.AI· Zijian Chen, Zheng Zhang, Miao Jia, Xingchen Hu, Weibo Gao, Linan Yue·· 11 小时前AI 评分29
Learner2Skill：将学习者行为外化为可复用技能，实现高效学习者模拟
From Learner Behavior to Reusable Skills for Effective and Efficient Learner Simulation
AI 导读
Learner2Skill 将历史交互中获得的学习者模拟能力外化为持久可复用的 Simulation Skill，避免重复处理不断增长的交互历史。该 Skill 记录学习者当前学习状态与反复出现的响应模式，随新交互持续演化，并可通过轻量 executor 校准适配新 LLM，无需从头重建学习者。
正文 · 原文
Abstract:Learner simulation aims to reproduce how a particular learner behaves on new tasks. Although Large Language Models (LLMs) can generate increasingly fine-grained learning behaviors, existing approaches often need to repeatedly process a growing interaction history to reconstruct the learner. This introduces additional context and inference costs and makes the acquired learner-specific simulation capability difficult to reuse across different LLMs. We therefore propose Learner2Skill, which externalizes the simulation capability acquired from historical interactions into a persistent and reusable Simulation Skill. The Skill captures the learner's current learning state and recurring response patterns, evolves as new real interactions arrive, and can be adapted to a new LLM through lightweight executor calibration without reconstructing the learner from scratch. Experiments show that Learner2Skill more faithfully reproduces fine-grained learner behavior while reducing overall token cost, and that the same constructed Skills can be effectively reused across different LLM executors.
| Comments: | 16 pages |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2609.37157 [cs.AI] |
| (or arXiv:2609.37157v3 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2609.37157 arXiv-issued DOI via DataCite |
Submission history
From: Zijian Chen [view email]
[v1]
Tue, 29 Sep 2026 09:47:57 UTC (9,727 KB)
[v2]
Fri, 2 Oct 2026 15:05:09 UTC (9,725 KB)
[v3]
Thu, 5 Nov 2026 02:30:18 UTC (8,947 KB)
来源：arXiv cs.AI · arxiv.org